Inspection Of Parts Research Articles

Grasp and Inspection of Mechanical Parts based on Visual Image Recognition Technology

In the process of industrial production, whether the machine can work stably is an important issue related to production efficiency and production safety. The cleaning of mechanical parts is an important factor affecting the stable operation of mechanical equipment, so the cleaning of mechanical parts is one of the important manufacturing links before assembly and manufacturing. The important value of the application of image recognition technology in the quality inspection of mechanical parts is briefly analyzed, and then the common problems in the quality inspection of mechanical parts are studied, the relevant measures of the application of image recognition technology in the quality inspection of mechanical parts are discussed, and finally the case analysis of the quality inspection of mechanical parts is carried out. The main purpose is to rationally use image recognition technology to complete the quality inspection of mechanical parts, so as to improve the overall level of production automation and give full play to the maximum role of this technology. At present, a variety of mechanical parts classification methods based on deep learning are studied. According to the demand of industrial machine parts, the corresponding machine parts data set is created. According to the production requirements, the SPP structure in the traditional YOLOV5 network is improved, and a new SPC structure is proposed: The YOLOv5 network with SPC structure is characterized by no pooling layer, which improves the accuracy and recall rate compared with the traditional YOLOv5 network. Secondly, the control method of robot grasping mechanical parts is studied. Using the camera to capture the image and the upper computer to calculate the mechanical parts under the camera coordinate system; Through camera calibration and hand-eye calibration, the transformation relationship between the grasping coordinates of mechanical parts in the camera coordinate system and the grasping coordinates of mechanical parts in the robot base coordinate system is obtained. The grasping coordinates and part type information of the mechanical parts in the robot base coordinate system are transmitted from the host computer to the robot through Modbus/TCP communication protocol.

Application of Ultrasonic Methods in Super POD Thickness Measurement Examination

NDT is a scientific field of engineering that includes testing and inspection of materials and equipment which is useful for evaluating a condition, finding deficiencies and defects, and also extending the useful life of the infrastructure used. The main difference between non-destructive testing and other forms of material evaluation is that non-destructive testing allows evaluation or inspection of parts on site without having to permanently modify or damage the part. In maintaining the credibility of the company's services, the company adopting NDT/NDE testing techniques in carrying out regular inspections or checks on the tools used, one of which is the application of the ultrasonic method on the Super POD (Programmable Optimum Density). Based on this background, the author chose the theme of the study to write a scientific paper entitled “Application of Ultrasonic Methods in Super POD Thickness Measurement Examination”. The SBF-624 Super POD (programmable optimum density, POD) is a trailer-mounted fracturing service blender that can blend and pump up to 120 barrels per minute of fracturing slurry. The Super POD computers precisely control the solid-to-liquid ratio of the prop pant at design values in either ramp or stair-step mode. The results of observations of objects that have been inspected using the ultrasonic method, namely measuring the thickness of the Super POD SBF 624, from the good results without any defects being detected, and cleaned in surface condition so it can be said that the machine has shown good effective results and can meet the standards for using tools for the company.

Automatic non-destructive UAV-based structural health monitoring of steel container cranes

Container cranes are of key importance for maritime cargo transportation. The uninterrupted and all-day operation of these container cranes, which directly affects the efficiency of the port, necessitates the continuous inspection of these massive hoisting steel structures. Due to the large size of cranes, the current manual inspections performed by expert climbers are costly, risky, and time-consuming. This motivates further investigations on automated non-destructive approaches for the remote inspection of fatigue-prone parts of cranes. In this paper, we investigate the effectiveness of color space-based and deep learning-based approaches for separating the foreground crane parts from the whole image. Subsequently, three different ML-based algorithms (k-Nearest Neighbors, Random Forest, and Naive Bayes) are employed to detect the rust and repainting areas from detected foreground parts of the crane body. Qualitative and quantitative comparisons of the results of these approaches were conducted. While quantitative evaluation of pixel-based analysis reveals the superiority of the k-Nearest Neighbors algorithm in our experiments, the potential of Random Forest and Naive Bayes for region-based analysis of the defect is highlighted.

Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization

Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this study proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the overlap between the discrepancy distributions (DDs) of normal and abnormal samples. With CDO, a large margin and a small overlap between normal and abnormal DDs are obtained, and the prediction reliability is boosted. Experiments on MVTec2D and MVTec3D show that CDO effectively mitigates the overgeneralization and achieves great anomaly localization performance with real-time computation efficiency. A real-world automotive plastic parts inspection application further demonstrates the capability of the proposed CDO. Code is available on https://github.com/caoyunkang/CDO.

Enhancement of various images using coefficients obtained from a class of Sakaguchi type functions

Digital image processing has a wide range of uses, including robotics and automated inspection of industrial parts. Other uses include remote sensing using satellites and other spacecraft, image transmission and storage for business applications, medical processing, and Acoustic image processing. The process of highlighting particular intriguing features in a hidden image is known as image enhancement. We can accomplish this by altering the brightness, contrast, etc. The generated output is more suitable than the original image for some particular purposes. The proposed algorithm which is based on the convolution of coefficient bounds of a subclass p-Upsilon {mathcal {S}}^*(t,delta ,mu ) obtained using Mittag-Leffler type Poisson Distribution is tested on three image data sets with different dimensions and image formats (PNG, JPEG, TIFF, etc.) and its PSNR, SSIM, MSE, RMSE, PCC and MAE values are observed to check the quality of the enhanced images.

First report of Sclerotinia sclerotiorum causing Sclerotinia wilt of hop (Humulus lupulus) in Poland.

The common hop (Humulus lupulus L., Cannabaceae) is a perennial plant cultivated in the temperate climate zone and used in the brewing and pharmaceutical industry. In June 2021, symptoms of wilting and subsequent drying of shoots were observed on hop plants (cv. Lubelski) in Lubelskie Province, in Poland (50°55'30.5"N, 22°10'35.4"E). Wilted shoots showed no symptoms of chlorosis. Usually both healthy and wilted shoots were present on the same plant. Approx. 20% of the plants in the 2 hectare hop garden showed these symptoms. An inspection of the underground parts of the infected shoots revealed a brown necrosis of the tissues partly covered by white mycelium with black sclerotia. These symptoms were characteristic for Sclerotinia sclerotiorum (Lib.) de Bary (Bolton et al. 2006), but this pathogen has never been detected in hop gardens in Poland before. In order to confirm the preliminary diagnosis, shoots from five different plants with symptoms of necrosis were collected, disinfected with 1% sodium hypochlorite for 1 min, rinsed with sterile water and dried. Twelve fragments from partially necrotized tissue were placed on potato dextrose agar (PDA) amended with chlortetracycline hydrochloride. After three days of incubation at room temperature and daylight, 75% of the explants had white or light grey mycelia present. Pure cultures were obtained by transplanting mycelium to fresh PDA. Within 4 days, the mycelium has reached the diameter of Petri dishes (90 mm). On PDA at room temperature and daylight, black spherical or cylindrical sclerotia formed after 6-14 days. Sclerotial size was 1.0 to 10.0 x 1.0 to 5.0 mm (average 2.8 x 2.0 mm; n = 57 from 3 plates). Five isolates were subjected to DNA extraction. Then ITS region was amplified and sequenced using primers ITS1/ITS4 (White et al. 1990). The sequences obtained from the five fungal isolates were identical with each other and BLAST analysis revealed also 100% identity with the GenBank records of S. sclerotiorum (e.g. KT224645, Baturo-Ciesniewska et al. 2017). One representative sequence of isolate Ss5HL was deposited to GenBank (OQ998981). Pathogenicity of the isolate Ss5HL was confirmed in inoculation tests on approx. 30 cm high, young shoots of hop plants (cv. Lubelski) grown from rootstock for 4 weeks in the greenhouse. Five plants were inoculated by placing mycelial discs from a 7-day-old culture on shoots and covering them with wet sterilized cotton pads and aluminum foil. Two control plants were treated in the same way but instead of mycelial discs pure agar discs were placed on the shoots. Then plants were kept in a climate chamber (80% relative humidity, 15-h light at 22°C, 9-h dark at 18°C). All fungal inoculated shoots wilted within 3-4 days, then necrosis developed and spread from the place of inoculation up the shoot. No tissue necrosis was observed below the place of inoculation. The control plants remained asymptomatic. The inoculation test was carried out twice with the same result. Fungal cultures reisolated from the inoculated shoots were morphologically identical with the culture used as inoculum. Isolate Ss5HL was deposited in the collection of the Westerdijk Fungal Biodiversity Institute (CBS 150077).To our knowledge, this is the first case of Sclerotinia wilt of hops in Poland and also in Europe, with the exception of one, nearly 100 years old report from the United Kingdom (Salmon and Ware 1936). S. sclerotiorum rarely occurs on hop but it can cause severe yield reduction if pathogen accumulates in the soil.

Advancements in Machine Vision for Automated Inspection of Assembly Parts: A Comprehensive Review

Advancements in Machine Vision for Automated Inspection of Assembly Parts: A Comprehensive Review

A generalized precision measuring mechanism and efficient signal processing algorithm for the eccentricity of rotary parts.

Rotary parts are widely used in transmission equipment, and the precision of the rotary parts determines the performance of the equipment. The accurate measurement and modification of eccentricity is a premise to ensure the parts' quality. However, the existing measurement methods have the shortcomings of low efficiency, complex operation, high costs and restricted applicability. To accurately and efficiently identify the rotary part's eccentricity parameters, including attitude angle, eccentricity and eccentric angle, a novel generalized precision measurement method is proposed in this study. Our method includes a lever measuring mechanism with a spherical probe, and a corresponding efficient signal processing algorithm to fit the measurement signal. The generalized measuring mechanism has a simple structure and can effectively measure arbitrary cross-sections, and its design and optimization principles are investigated and given thoroughly. The signal processing algorithm, based on Fourier expansion and least squares, can efficiently extract the eccentricity parameters of measured cross-sections. The proposed generalized precision measurement method has proven to overcome the limitations of existing methods, exhibits strong resistance to interference and enables batch inspection of rotary parts with a single adjustment. Its effectiveness, efficiency, applicability and repeatability are evaluated by simulation calculation and experimental verification. The proposed method has great potential in broad applications, such as detecting eccentricity and correcting errors for mechanical measurements, aerospace, equipment manufacturing, and other related fields.

Body Checking in Anorexia Nervosa: from Inquiry to Habit

AbstractBody checking, characterized by the repeated visual or physical inspection of particular parts of one’s own body (e.g. thighs, waist, or upper arms) is one of the most prominent behaviors associated with eating disorders, particularly Anorexia Nervosa (AN). In this paper, we explore the explanatory potential of the Recalcitrant Fear Model of AN (RFM) in relation to body checking. We argue that RFM, when combined with certain plausible auxiliary hypotheses about the cognitive and epistemic roles of emotions, is able to explain key characteristics of body checking, including how body checking behavior becomes habitual and compulsive.

What alternatives to computed tomography for inspection of additive manufacturing parts with channels

Non-destructive inspection of parts with small diameter channels is a major challenge. Additive Manufacturing (AM) offers many advantages compared to the traditional subtractive manufacturing process for the manufacturing of these complex structures. Thales, Safran and ArianeGroup joined forces to find a way to inspect parts with small diameter channels by technics other than X-ray computed tomography. LNE and Institut de Soudure (French welding institute) worked with them to identify, propose and test non-destructive techniques capable to detect flaws and cavities containing unfused powder unique to the powder-bed fusion AM process category. This paper will present some results of this project called FA- Canalsafe®. Artificial defects created on mock-ups will be described. Some results and limitations on eddy current testing and on visual endoscopy will be discussed. Finally, some recommendations on NDT implementation will be proposed.

A Model Review on Joint Optimization of Part Quality Inspection Planning, Buffer Allocation, and Preventive Maintenance in SMMS

In serial multi-stage manufacturing systems (SMMS), optimization of part quality inspection planning (PQIP), buffer allocation problem (BAP), and preventive maintenance (PM), individually and jointly, is attracting researchers’ attention. The model formulation for complicated manufacturing systems and the previously mentioned joint decisions is very beneficial given the interdependencies between the various manufacturing functions. As a result, this paper evaluates the literature on joint optimization of the multi-stage serial production system. The literature is classified based on the decision variables basis to represent each manufacturing function [inspection sample size and allocation (PQIP), buffer sizing and allocation (BAP), and preventive maintenance scheduling (PM)], and a general example model is presented in each classification, with a summary of recent studies, solution methods, research gaps, and future research recommendations. In the integrated models, almost all the studies considered only two functions, with that it is worth noting that research into the optimization of over two functions is still in its beginning. Furthermore, most studies neglected many of the real industrial settings that should also be integrated into the model. And finally, there was no specific solution technique recommended in the literature, yet a general simulation optimization method was used to generate and evaluate the combinatorial complex joint models.

THREE-FREQUENCY METHOD FOR DETERMINING THE EQUIVALENT SIZE OF THE DISCONTINUITY DURING MANUAL ULTRASOUND CONTROL

The work is devoted to topical issues of increasing the reliability and informativeness of the results of manual ultrasonic inspection of parts and assemblies of technical objects. The paper presents a three-frequency method of ultrasonic flaw detection, which makes it possible to increase the reliability of the non-etalon method for determining the type of discontinuity detected as a result of ultrasonic testing. The developed method makes it possible to determine the type of discontinuities of various types. The NDTRT-26 software product has been developed to automate calculations using the three-frequency method.

Automatic Inspection System for Segregation of Defective Parts of Heavy Vehicles

Defect Detection is a crucial process in the manufacturing industry. Most of the manufacturing parts tend to get scratches, dents, etc. on their surface during the manufacturing process. Such parts are defective and are not acceptable for further use. So, it is essential to inspect parts before they can be dispatched further. To detect such defects, a team of skilled persons is deployed; which does manual visual inspection of parts to detect those defects. In manual inspection, chances of missing small defects are pretty high. Not only that but it also takes a considerable amount of time. Moreover, the job is tedious and monotonous creating strain on the eyes of members of the inspection team. Some defects are even not visible to the naked eye. To make the process of visual inspection simple and easy, a deep learning Convolutional neural network (CNN) based model is proposed. Reason behind choosing a convolutional neural network is its capability to extract features efficiently as the task accuracy depends upon this capability. A custom dataset has been prepared with utmost care of illumination conditions, resolution of image, etc., so that a clear picture of parts with minute details can be captured. The model has been trained using the dataset thus prepared and containing 960 images and it is observed that it provides a good accuracy of 95%. The same model is deployed using an embedded board with a Jetson Nano processor to prepare a computer vision-based inspection system that can be used to differentiate between perfect and imperfect parts and thus help skilled personnel in the inspection process.

A flexible deep learning framework for thermographic inspection of composites

Infrared thermography (IRT) is a promising inspection technique, showing good defect detectability in a range of materials. To advance the IRT inspection technique, automated defect detection and analysis are of high interest. This study proposes an object detection algorithm based on Faster R–CNN with attention-based feature fusion network and flexible late fusion strategy for efficient extraction of defect features from an IRT image sequence. In order to train the deep learning-based algorithm, a large, diverse and representative virtual thermographic dataset for composite materials was constructed by an in-house developed parameterized 3D finite element simulator. The virtually trained deep learning framework is tested on experimental IRT datasets which were obtained on composite coupons having a range of artificial defect types as well as on stiffened aerospace composite panels with real (production) defects. The obtained test results indicate the high performance, generalization and reliability of the proposed deep learning framework for automated thermographic inspection of composite parts.

Acoustic material testing a progressive testing method

Acoustic material testing is well known for quality inspection of metal and composite parts in serial production, with short cycle times and a robust performance. Acoustic material testing is a referencing respectively comparative testing method. Therefore, preclassified reference parts are required to teach the testing system. In practice, it is often difficult to provide clearly pre-classified failure parts. Also, it is common to use sample parts which are characterized by the subjective evaluation of the employees. In this case evaluation deviations between the subjective evaluation and the objective measurement result of the acoustic test system are to be considered. This leads to discussions, as the employees tend to trust their own judgment and rely on their experience. Defects must then be clearly determined, by using other and more complex and costly testing methods, such as ultrasound or CT. With new analytic techniques the teaching process, especially without the availability of failure parts, can be shortened and simplified.

Synchronism system for generating ultrasonic images of complex geometry pieces using industrial robots

This paper presents a synchronism system that has been designed to facilitate the generation of ultrasonic images of pieces with complex geometry through the use of industrial robots. Modern robotic manipulators and, more specifically, industrial robotic arms integrated with server computers, sensors and actuators have revolutionized the way automated non-destructive testing is performed. Currently there are commercial industrial robots that have the precision, speed and repetitiveness in their movements that make them suitable for use in numerous non-destructive testing inspections whose designs are carried out by small and medium sized specialized companies. Automatic ultrasonic inspection of complex parts remains one of the most difficult challenges according to the specific and increasingly exigent demands of the markets. The closed configuration of these complex robotic arms makes it difficult to maintain adequate synchronism between the movement of the robot and the acquisition of the data, making it difficult to generate ultrasonic images consistent with the geometry of the part. This is a serious problem in the inspection of aerospace components where high quality is necessary to assess the condition of the inspected component. In this paper, we present an autonomous independent external system that provides control signals to synchronize the ultrasound system with the robot trajectories without needing to access its position in real time. A methodology to obtain the timing pattern for a given part inspected with a given robotic system will also be presented here.

Automated misalignment correction method for ultrasonic inspection of CFRP parts

Ultrasonic inspection of large CFRP components requires an accurate positioning of the part with respect to the equipment’s coordinate system to ensure normal incidence during the scan. Fulfilling this condition often implies impractical and time-consuming manual adjustments of the part. A new method is proposed for ultrasonically determining the position of a complex part installed in an inspection system, and automatically correcting the offline-programmed path instead of iteratively and manually adjusting the part’s position. Two application strategies of our method are presented and experimentally tested on a complex CFRP landing gear component. The results suggest that even the simplest strategy using a planar learning scan of a randomly positioned part can produce C-scans of equal quality as those obtained with the manual alignment, in a fraction of the time that this process usually takes.

Automatic Methods for Ultrasonic Scanning Paths Generation

This paper presents the last evolutions of a program developed in 2020 for the automated generation of optimal scanning paths for 0°LW ultrasonic inspections of complex parts. After summarizing the overall concepts of the path generation method, the paper presents two new algorithms (side following path and side/radius interpolating path) recently developed for specific geometries such as long and thin parts, or parts including nonparallel radii. Trajectories automatically generated by the software are then presented for a collection of various aerospace and industrial CFRP components. The results show that the software was able to generate optimal paths for all the tested geometries, using the part’s 3D surface CAD and the probe’s characteristics as only inputs. In particular, the addition of the new algorithms allows for the generation of satisfactory trajectories even for the parts that were previously problematic.

A Generative Design Method for Typical Structural Parts of Aircraft

Typical structural parts of aircraft are the main frame of the aircraft and the carrier of other parts and equipment. Their good design is the basis to ensure the overall performance of aircraft and reduce maintenance costs. If the selection estimation, parameter setting, and model normative inspection of typical structural parts are carried out manually, the design quality and efficiency of large quantities of structural parts will be low especially. In this paper, a generative design method for typical structural parts of aircraft is proposed. Based on the introduction of the design framework, the intelligent design of 3D models for typical structural parts of aircraft is elaborated by taking shear slices of aircraft as an example. It includes the intelligent recommendation of the structural scheme, intelligent design of structural parameters, and intelligent generation of the 3D model. Engineering implementation shows that the proposed method greatly improves the design efficiency and the overall quality of the aircraft.

Inspection of aircraft parts by eddy current method

Aviation technologies are developing due to the need for advancements at military field and the increase in commercial air transportation. The development of aviation technology also forces the development of Non-Destructive Testing (NDT) Standards. The accuracy of these inspections, their fast results and their applicability on many materials is one of the important issues to be studied. Eddy current testing, which has a significant advantage in terms of test speed and accuracy, is one of the main methods used in the non-destructive testing of aircraft parts. The test is used not only in metal and metal alloy materials, but also in composite materials with high conductivity such as carbon fiber to detect failures. Also, improvements at the eddy current test system and probes play a major role in the failure assessment of aircraft parts. In this article, comprehensive technical information about the eddy current testing method is given and the case studies are presented.